Metadata-Aware Adaptation of a Generative Foundation Model for Conditional CMR Synthesis
Authors: Marc Rodríguez, Grzegorz Skorupko, Nay Aung, Steffen E Petersen, Karim Lekadir, Polyxeni Gkontra
Organizations: Facultat de Matem`atiques i Inform`atica, Universitat de Barcelona, Spain · Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM), Facultat de Matem`atiques i Inform`atica, Universitat de Barcelona, Spain · William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University London, Charterhouse Square, London, UK · Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, West Smithfield, London, UK · Instituci´o Catalana de Recerca i Estudis Avanc¸ats (ICREA), Passeig Llu´ıs Companys 23, Barcelona, Spain
Synthetic image generation is a promising strategy to address data scarcity and the underrepresentation of clinically important phenotypes in medical imaging, yet generating images that faithfully reflect meaningful patient characteristics remains challenging. In this work, we investigate metadata-conditioned cardiac magnetic resonance (CMR) synthesis using a pretrained latent diffusion model, encoding structured clinical metadata and slice position as textual prompts to guide CMR generation. To improve metadata adherence and address the imbalance of clinical attributes, we integrate three strategies: Metadata-Free Classifier-Free Guidance (CFG), Contrastive Batching, and Inverse-Frequency Sampling. The framework was fine-tuned and evaluated on 59,058 short-axis CMR from the UK Biobank using paired image similarity, distributional fidelity, and subgroup-level analyses. The combined approach achieved a Fréchet Inception Distance (FID) of 37.47, improving by 57.04% over the same model fine-tuned without these strategies and by 28.68% over a previous text-conditioned CMR diffusion baseline requiring cardiac geometry as additional input, while relying solely on patient metadata. This distributional gain, driven mainly by Metadata-Free CFG, came with a modest reduction in paired similarity, suggesting that the model prioritizes population-level realism over exact image reproduction. Subgroup analyses demonstrated improved alignment across demographic and acquisition-related metadata, with disease-specific conditioning being the most challenging task. These findings demonstrate the potential of generative foundation models for clinically meaningful CMR synthesis while highlighting the need for more effective metadata-aware conditioning strategies. Our code is available at https://github.com/rodriguezmarc/conditional-cmr.
Figures & tables
Fig. 1: Overview of the combined conditional CMR image generation pipeline. Target CMR characteristics are encoded as text prompts and fed to a pretrained latent diffusion model, which is then fine-tuned using the proposed techniques to improve metadata adherence and mitigate class imbalance during training.
Metric
Fine-tuned SD
MF-CFG
MF-CFG+IFS
MF-CFG+CB
MF-CFG+IFS+CB
Skorupko et al. [ 15 ]
MAE ↓
0.257±0.040
0.254±0.045
0.261±0.041
0.263±0.042
0.260±0.043
0.253±0.040
MS-SSIM ↑
0.192±0.075
0.177±0.079
0.164±0.072
0.163±0.073
0.171±0.076
0.266±0.075
FID ↓
87.22
44.84
39.12
37.08
37.47
52.54
FRD ↓
4.76
4.64
4.27
4.44
4.64
5.65
MAE DR → 1
0.931±0.189
1.010±0.127
1.006±0.178
1.050±0.185
1.026±0.191
1.248±0.178
MS-SSIM DR → 1
0.940±0.126
1.081±0.197
1.0323±0.120
1.056±0.122
1.063±0.126
1.068±0.111
TABLE I: Paired and distributional fidelity metrics together with the MAE and MS-SSIM diversity ratios (DR). Standard deviations for the DR were obtained by first-order error propagation. ↓ / ↑ indicate that lower/higher values are better; for DR, values closer to 1 ( → 1) indicate agreement with the reference distribution. Metadata-aware strategies are added incrementally on the fine-tuned Stable Diffusion (SD) baseline. Abbreviations: MF-CFG, Metadata-Free Classifier-Free Guidance; IFS, Inverse-Frequency Sampling; CB, Contrastive Batching.
Fig. 2: Representative generated CMR images by BMI category showing the conditioning effect on generation. From underweight to obese, the generated images qualitative show progressively greater adipose tissue, consistent with increasing BMI. The three rightmost images were generated from the same obese conditioning prompt using different random seeds, demonstrating the diversity achievable under identical conditioning.
Fig. 3: Subgroup distributional fidelity (FID) matrices for each metadata attribute. Columns correspond to generated subgroups and rows to reference subgroups. Abbreviations: NOR, normal; OB, obese; OW, overweight; UW, underweight; AF, atrial fibrillation; HLTH, healthy; HF, heart failure; IHD, ischemic heart disease; MI, myocardial infarction; F, female; M, male; MV, mid-ventricular.
Synthetic cardiac MRI (CMRI) generation has emerged as a promising strategy to overcome the scarcity of annotated medical imaging data. Recent advances in GANs, VAEs, diffusion probabilistic models, and flow-matching techniques aim to generate anatomically accurate images while addressing challenges such as limited labeled datasets, vendor variability, and risks of privacy leakage through model memorization. Maskconditioned generation improves structural fidelity by guiding synthesis with segmentation maps, while diffusion and flowmatching models offer strong boundary preservation and efficient deterministic transformations. Cross-domain generalization is further supported through vendor-style conditioning and preprocessing steps like intensity normalization. To ensure privacy, studies increasingly incorporate membership inference attacks, nearest-neighbor analyses, and differential privacy mechanisms. Utility evaluations commonly measure downstream segmentation performance, with evidence showing that anatomically constrained synthetic data can enhance accuracy and robustness across multi-vendor settings. This review aims to compare existing CMRI generation approaches through the lenses of fidelity, utility, and privacy, highlighting current limitations and the need for integrated, evaluation-driven frameworks for reliable clinical workflows.
Department of Computer Engineering, University of Peradeniya, Peradeniya, Sri Lanka · Department of Computer Engineering, University of Maryland, College Park, USA · Department of Holistic Systems, SimulaMet, Oslo, Norway
Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models. To address this limitation, we propose a generative method for synthesizing temporally coherent and anatomically consistent cardiac sequences. Our text-to-video framework decouples cardiac spatial structure from temporal motion. First, a fine-tuned diffusion model synthesizes an initial frame from a clinical text prompt, controlling anatomical features. Then, a latent flow model conditioned on a cardiac phase embedding generates the complete cardiac motion, ensuring spatial consistency and temporal control. Our model generates anatomically and pathologically diverse sequences with high temporal coherence and strong fidelity to input prompts, achieving a FID of 31.68 for image realism and a CLIP score of 31.04 for text-image alignment. These experimental results highlight its potential to produce high-fidelity, on-demand medical data, offering a scalable solution to data scarcity.
SyCoIA - IMT Mines Alès · Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China · SyCoIA, IMT Mines Ales, Ales, France
Deep learning in cardiac MRI (CMR) is fundamentally constrained by both data scarcity and privacy regulations. This study systematically benchmarks three generative architectures: Denoising Diffusion Probabilistic Models (DDPM), Latent Diffusion Models (LDM), and Flow Matching (FM) for synthetic CMR generation. Utilizing a two-stage pipeline where anatomical masks condition image synthesis, we evaluate generated data across three critical axes: fidelity, utility, and privacy. Our results show that diffusion-based models, particularly DDPM, provide the most effective balance between downstream segmentation utility, image fidelity, and privacy preservation under limited-data conditions, while FM demonstrates promising privacy characteristics with slightly lower task-level performance. These findings quantify the trade-offs between cross-domain generalization and patient confidentiality, establishing a framework for safe and effective synthetic data augmentation in medical imaging.
University of Peradeniya, Sri Lanka · University of Maryland, College Park, USA · Tulane University School of Medicine, USA; Simula Research Laboratory, Norway +1